7512c3ad20
* add debug guide * add background * add .gitignore * Update devtools/dev_sharegpt.yml Co-authored-by: Wing Lian <wing.lian@gmail.com> * Update docs/debugging.md Co-authored-by: Wing Lian <wing.lian@gmail.com> * simplify example axolotl config * add additional comments * add video and TOC * try jsonc for better md rendering * style video thumbnail better * fix footnote --------- Co-authored-by: Wing Lian <wing.lian@gmail.com>
50 lines
955 B
YAML
50 lines
955 B
YAML
# Example config for debugging the sharegpt prompt format
|
|
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
|
|
model_type: LlamaForCausalLM
|
|
tokenizer_type: LlamaTokenizer
|
|
is_llama_derived_model: true
|
|
|
|
load_in_8bit: true
|
|
load_in_4bit: false
|
|
|
|
datasets:
|
|
- path: philschmid/guanaco-sharegpt-style
|
|
type: sharegpt
|
|
shards: 10
|
|
val_set_size: 0
|
|
output_dir: temp_debug/axolotl_outputs/model
|
|
dataset_prepared_path: temp_debug/axolotl_outputs/data
|
|
dataset_processes: 1
|
|
|
|
sequence_len: 4096
|
|
sample_packing: false
|
|
pad_to_sequence_len: true
|
|
|
|
adapter: lora
|
|
lora_model_dir:
|
|
lora_r: 32
|
|
lora_alpha: 16
|
|
lora_dropout: 0.05
|
|
lora_target_linear: true
|
|
lora_fan_in_fan_out:
|
|
|
|
micro_batch_size: 1
|
|
num_epochs: 1
|
|
max_steps: 10
|
|
optimizer: adamw_bnb_8bit
|
|
lr_scheduler: cosine
|
|
learning_rate: 0.0002
|
|
|
|
train_on_inputs: false
|
|
group_by_length: false
|
|
bf16: false
|
|
fp16: true
|
|
tf32: false
|
|
|
|
gradient_checkpointing: true
|
|
logging_steps: 1
|
|
flash_attention: true
|
|
|
|
warmup_steps: 10
|
|
weight_decay: 0.0
|